© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260821
    Prev
    Next
    INDEX
    Explanations

    chat GPT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    1.16
    ki
    1.13
    are
    1.06
    ko
    1.02
    po
    0.96
    ksi
    0.96
    ;,
    0.96
    has
    0.95
    ;
    0.95
    ca
    0.95
    POSITIVE LOGITS
    as
    1.48
    at
    1.47
    يش
    1.44
    טן
    1.31
    ات
    1.28
    ות
    1.26
    يح
    1.23
    ه
    1.23
    يت
    1.22
    يث
    1.22
    Activations Density 0.000%

    No Known Activations